Made on
Aug 4, 2026
Price at call
$265.23
6-month call
Neutral +3.9%
Target by Feb 2027
$275.50
Great value below
$225.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
+3.9% to $275.50
Predicted High
$275.50
at 6 months
Predicted Low
$261.00
at 1 month
Max Drawdown (predicted)
-1.6%
Forecast
The masterbrain trajectory — 7 dated checkpoints. Short rungs (2w, 1m) show the typical range as the primary claim; point calls run from 2 months out. Every claim still gets graded. Predicted Aug 4, 2026 1:18 am
Neutral
MCD trends range-bound to
$275.50
(+3.9% from $265.23)
by Feb 2027.
dip-then-recover
ThesisMCD is a low-beta defensive that has already absorbed a -15.8% drawdown and trades below the anchored-PE fair value of $338. With no imminent earnings catalyst, a mild sentiment headwind, and a risk-on tape that ignores defensives short-term, expect a shallow drift lower over the first month before value gravity and a Q3 print pull the stock back toward the mid-270s by winter.
Invalidated ifA break below $250 on consumer-stress news, or a move above $285 without an earnings catalyst, would falsify the shallow-recovery thesis.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $265.23 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 4, 2026 | — | $265.23 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 18, 2026 | $253.59–$276.87 typical range · internal point $263.50 | — | ±4.4% | 6/10 | Risk-on tape ignores defensives, mild sentiment drag |
| What actually happened: closed $265.53 on Aug 17, 2026 = +0.1% vs the call (predicted -0.7%) · direction HIT (called flat, was flat) · off by 0.8 pp · accuracy 10/10 · typical range ±4.4%: inside the band · S&P +0.6% over the same window — lagged it | ||||||
| 1 month | Sep 4, 2026 | $248.37–$282.09 typical range · internal point $261.00 | — | ±6.4% | 5/10 | Consumer-stress narrative caps upside pre-print |
| What actually happened: closed $259.63 on Sep 3, 2026 = -2.1% vs the call (predicted -1.6%) · direction HIT (called flat, was flat) · off by 0.5 pp · accuracy 10/10 · typical range ±6.4%: inside the band · S&P -0.9% over the same window — beat it | ||||||
| 2 months | Oct 4, 2026 | $264.00 | — | -0.5% | 4/10 | October drift, low beta dampens macro moves |
| What actually happened: closed $231.89 on Oct 2, 2026 = -12.6% vs the call (predicted -0.5%) · direction MISS (called flat, was down) · off by 12.1 pp · accuracy 4/10 · S&P -0.2% over the same window — beat it | ||||||
| 3 months | Nov 4, 2026 | $270.00 | — | +1.8% | 5/10 | Q3 earnings beat likely given 4-of-4 streak |
| 4 months | Dec 4, 2026 | $273.00 | — | +2.9% | 5/10 | Post-print re-rating toward anchored-PE fair value |
| 5 months | Jan 4, 2027 | $272.00 | — | +2.6% | 4/10 | January tax-loss reversal, defensive rotation |
| 6 months | Feb 4, 2027 | $275.50 | — | +3.9% | 4/10 | Value gravity toward $338 anchor, slow grind |
Why ranges on the short rungs?
A 102-prediction trial (2026-07-21) showed 2-week point calls carry no information here —
three prompt formulations all lost to simply predicting zero — while the stock's own
volatility scale (σ×√t) described those windows well. So the short rungs claim what's
actually knowable: the typical travel, with earnings timing flagged where the variance
will come from. The internal point calls keep being generated and graded to map where
real skill begins. Full evidence: stocks/predictions/V0.5-DESIGN.md §8.
Deterministic control (v0.3 value line) targets $70,631,588.51 (+26,630,215.5%) — both lines get graded at every checkpoint, so the brain has to beat the formula, not just replace it. Brain: claude-opus-4-7.
Weaknesses
No weaknesses recorded for this run.All inputs present, no fallbacks used — nothing to flag.
Equation Inputs
Everything feeding the v0.6.0 model — value anchors, the stock's own price behaviour, and the tunable knobs.Value anchors (from deep analysis)
| Price at call | $265.23 |
| Composite fair value | $134,163,615.62 |
| Signal-adjusted fair value | $158,420,061.73 |
| DCF fair value | $184,760,943.21 |
| Anchored-PE fair value | $338.06 |
| Buy-below (value lens) | $225.00 |
| Value net score | -48 |
| Value confidence | 7 / 10 |
| Quality net score | +79 |
| Memo confidence | 8 / 10 |
| Deserved value (base) | — |
| Quality tilt | — |
| Deserved value (used) | — |
| Coherence (value × quality) | — |
Price behaviour (trailing — shapes the realism line)
| Realized volatility (annualized) | 1m 20.8% 3m 22.0% 6m 20.3% |
| Daily σ (realism noise) | 1.4% |
| Beta vs S&P 500 | 1m -0.18 3m -0.27 5m 0.07 |
| Trailing 6-month return | -15.8% |
Knobs (equation params)
| ladder | ["w2","m1","m2","m3","m4","m5","m6"] |
| llm_model | claude-opus-4-7 |
| max_tokens | 3000 |
| control_knobs | {"w_dcf":0.5,"k_qual":0.200000000000000011102230246251565404236316680908203125,"reach_6m":0.450000000000000011102230246251565404236316680908203125,"coh_floor":0.5,"conf_gain":0.059999999999999997779553950749686919152736663818359375,"noise_phi":0.84999999999999997779553950749686919152736663818359375,"conf_floor":0.40000000000000002220446049250313080847263336181640625,"w_composite":0.5,"noise_window":"3m","flat_band_pct":5,"horizon_months":6,"noise_sigma_fallback":0.01499999999999999944488848768742172978818416595458984375} |
| Neutral band (%) | 5 |
| earnings_brief | v1 |
| prompt_version | p1 |
| control_version | v0.3.0 |
Version & Tech Chain
What produced this prediction — stamped on the record so versions can be compared by success rate later.
Model
v0.6.0
#271041f8fcd5 Tech composition (what this version is built from)
| # | Process | Kind | Group |
|---|---|---|---|
| 1 | Synthesis valuation-synthesis |
deterministic | final |
| 2 | Scenario Analysis scenario-valuation |
deterministic | valuation |
| 3 | Valuation / Mispricing ext-lens-value |
llm | extended |
| 4 | Company Quality ext-lens-quality |
llm | extended |
| 5 | Forensic Memo (combiner) ext-forensic-memo |
llm | extended |
| 6 | Classification company-classification |
llm | foundation |
| 7 | Live Quote fmp-quote |
data | market-data |
Inputs used (the runs that fed this prediction)
| Upstream process | Ran | Lag | Run id |
|---|---|---|---|
company-classification |
Aug 4, 2026 | freshest | MCD-20260804-000624-69b5 |
ext-forensic-memo |
Aug 4, 2026 | freshest | ext-MCD-20260804-005941-4e55 |
ext-lens-quality |
Aug 4, 2026 | freshest | ext-MCD-20260804-005941-4e55 |
ext-lens-sentiment |
Aug 4, 2026 | freshest | ext-MCD-20260804-005941-4e55 |
ext-lens-value |
Aug 4, 2026 | freshest | ext-MCD-20260804-005941-4e55 |
valuation-synthesis |
Aug 4, 2026 | freshest | MCD-20260804-000624-69b5 |
Inputs flagged 7d+ behind the freshest one may be stale relative to the rest of the analysis.
Saved History
2 frozen snapshots — the record we score once predictions mature.| Made | Model | Call | At call | Target | Exp. | Eval due | |
|---|---|---|---|---|---|---|---|
| Aug 4, 2026 | v0.6.0 | Neutral | $265.23 | $275.50 | +3.9% | Feb 2027 | viewing |
| Jun 27, 2026 | v0.3.0 | Neutral | $269.76 | $260.37 | -3.5% | Dec 2026 | view |
Not Yet Modeled
What this v0.6.0 forecast deliberately ignores — the work ahead, in plain sight.- Scenario probabilities — one path, no bull/bear split (base_prob = 1.0).
- Intraday / sub-2-week behaviour — the first claim is at 14 days by design (EOD product).
- Position sizing / portfolio context — the path is a price claim only.